10 papers
Hierarchical Credit Assignment for RLVR on Fused Gromov-Wasserstein Geometry
Qi Yu, Ruizhong Qiu, Zhichen Zeng +6
Reinforcement learning with verifiable rewards (RLVR) has been shown to improve the reasoning capability of large language models (LLMs) across diverse reasoning tasks. However, gr…
RankEvolve: A Reliable Multi-Agent Auto-Research Harness for Evolving Ranking Models
Zheng Chen, Linfeng Liu, Hong Li +1
Auto-research agents, LLM systems that propose, implement, train, and evaluate model changes across iterations, promise to automate applied ML's experimental loop. Over long horizo…
Inference-Time Graph Engineering for Multi-Agent LLM Workflows
Katherine Tieu, Dongqi Fu, Yinglong Xia +3
Recent multi-agent LLM systems increasingly rely on graph-structured communication to coordinate specialized agents. We revisit multi-agent orchestration from a graph-engineering p…
RankGraph-2: Lifecycle Co-Design for Billion-Node Graph Learning in Recommendation
Renzhi Wu, Zikun Cui, Junjie Yang +10
Graph-based retrieval at billion-node scale requires jointly solving three tightly coupled problems -- graph construction, representation learning, and real-time serving -- yet exi…
KVEraser: Learning to Steer KV Cache for Efficient Localized Context Erasing
Mufei Li, Shikun Liu, Dongqi Fu +5
Post-hoc context erasing over the KV cache is challenging because a local edit has a global consequence: once a span has been processed, its influence propagates into the cached st…
CMSL: Constructive Multi-Sequence Learning for Recommendation Systems
Zikun Cui, Renzhi Wu, Junjie Yang +10
Sequence learning has emerged as the promising paradigm in recommendation systems, surpassing traditional Deep Learning Recommendation Models (DLRM) by capturing the temporal nuanc…
Structuring and Tokenizing Distributed User Interest Context for Generative Recommendation
Ruizhong Qiu, Yinglong Xia, Dongqi Fu +6
Generative recommendation is an emerging paradigm that has shown promise in industrial recommendation systems, aiming to predict users' next interactions from their historical beha…
Towards Direct Latent-Space Synthesis for Parallel Branches in LLM-Agent Workflows
Shikun Liu, Mufei Li, Dongqi Fu +5
Large language models increasingly serve as execution engines for agentic systems, yet they still consume context through a sequential text interface. This creates a mismatch with…
ChronoID: Infusing Explicit Temporal Signals into Semantic IDs for Generative Recommendation
Dongdong Nian, Dongqi Fu, Chenliang Xu +4
Semantic IDs are crucial in generative recommendation, but with a fundamental limitation: temporal information is not well incorporated into semantic IDs. Instead, time influences…
RankGraph: Unified Heterogeneous Graph Learning for Cross-Domain Recommendation
Renzhi Wu, Junjie Yang, Li Chen +3
Cross-domain recommendation systems face the challenge of integrating fine-grained user and item relationships across various product domains. To address this, we introduce RankGra…